From vibe coding to professional AI-driven software development. One day, hands-on, for experienced developers who are ready for the next step.
Most experienced developers have tried using AI in a browser by now — ask a question, get an answer, copy some code. It's useful. But it's not what AI can do.
This course is about the next step: what happens when you let AI loose on your real codebase? What does it demand in terms of discipline, structure, and understanding — and how do you avoid things going wrong? We use Claude Code as our example tool, but the same principles apply across GitHub Copilot, OpenAI Codex, and most other agentic AI development tools that run directly on your machine.
You leave with something you've built, a clear methodology, and concrete tools to build the frameworks your organisation needs.
After the course, you will be able to:
The course is not a list of prompts to copy. It's a way of thinking you take back and adapt to your own context.
— Bo Frese
Five modules, alternating between teaching, demo, and hands-on exercises. The day is structured so each module builds on the last.
Format: One day (9:00–17:00), teaching alternates with hands-on exercises. Available in Danish and English.
Delivery: Primarily as in-house training at your premises. Content and focus can be aligned to your technological context, adjusted in length, or combined into a longer programme.
Who it's for: Experienced software developers — minimum mid-level. This course is not about learning to code. It's about learning to work with AI as a professional development partner.
What to bring: A laptop with your agentic AI tool installed and ready. A small hobby or side project to work on during exercises. A Claude Pro subscription is likely sufficient — the course alternates between theory, demo, and hands-on work, so you won't be burning tokens all day.
I'm a software developer and management consultant with over 30 years of experience — as a developer, architect, team lead, startup founder, and product owner. I still build products today, including an iOS app, a custom CMS, and an open-source AI development toolkit.
A year of intensive AI-assisted development changed how I work fundamentally — and made clear what goes wrong when organisations are seduced by how convincing it looks. This course draws directly from that experience. Not theory. Not research. What actually happened, and what I'd do differently.
In the end, it's developers who have to stand behind the quality of what gets built. That's what this course is about.
Bo Frese